aboutsummaryrefslogtreecommitdiffstats
path: root/library/cpp/yson_pull/detail/cescape_encode.h
diff options
context:
space:
mode:
authorAnton Samokhvalov <pg83@yandex.ru>2022-02-10 16:45:17 +0300
committerDaniil Cherednik <dcherednik@yandex-team.ru>2022-02-10 16:45:17 +0300
commitd3a398281c6fd1d3672036cb2d63f842d2cb28c5 (patch)
treedd4bd3ca0f36b817e96812825ffaf10d645803f2 /library/cpp/yson_pull/detail/cescape_encode.h
parent72cb13b4aff9bc9cf22e49251bc8fd143f82538f (diff)
downloadydb-d3a398281c6fd1d3672036cb2d63f842d2cb28c5.tar.gz
Restoring authorship annotation for Anton Samokhvalov <pg83@yandex.ru>. Commit 2 of 2.
Diffstat (limited to 'library/cpp/yson_pull/detail/cescape_encode.h')
-rw-r--r--library/cpp/yson_pull/detail/cescape_encode.h188
1 files changed, 94 insertions, 94 deletions
diff --git a/library/cpp/yson_pull/detail/cescape_encode.h b/library/cpp/yson_pull/detail/cescape_encode.h
index d1dae0f96e..bf5765f1d9 100644
--- a/library/cpp/yson_pull/detail/cescape_encode.h
+++ b/library/cpp/yson_pull/detail/cescape_encode.h
@@ -6,109 +6,109 @@
// Turns UTF-8 strings into unreadable garbage for no known reason
//#define CESCAPE_STRICT_ASCII
-namespace NYsonPull {
- namespace NDetail {
- namespace NCEscape {
- namespace NImpl {
- inline ui8 hex_digit(ui8 value) {
- constexpr ui8 hex_digits[] = "0123456789ABCDEF";
- return hex_digits[value];
- }
+namespace NYsonPull {
+ namespace NDetail {
+ namespace NCEscape {
+ namespace NImpl {
+ inline ui8 hex_digit(ui8 value) {
+ constexpr ui8 hex_digits[] = "0123456789ABCDEF";
+ return hex_digits[value];
+ }
- inline ui8 oct_digit(ui8 value) {
- return '0' + value;
- }
+ inline ui8 oct_digit(ui8 value) {
+ return '0' + value;
+ }
- inline bool is_printable(ui8 c) {
+ inline bool is_printable(ui8 c) {
#ifdef CESCAPE_STRICT_ASCII
- return c >= 32 && c <= 126;
+ return c >= 32 && c <= 126;
#else
- return c >= 32;
+ return c >= 32;
#endif
- }
+ }
- inline bool is_hex_digit(ui8 c) {
- return (c >= '0' && c <= '9') || (c >= 'A' && c <= 'F') || (c >= 'a' && c <= 'f');
- }
+ inline bool is_hex_digit(ui8 c) {
+ return (c >= '0' && c <= '9') || (c >= 'A' && c <= 'F') || (c >= 'a' && c <= 'f');
+ }
- inline bool is_oct_digit(ui8 c) {
- return c >= '0' && c <= '7';
- }
+ inline bool is_oct_digit(ui8 c) {
+ return c >= '0' && c <= '7';
+ }
- constexpr size_t ESCAPE_C_BUFFER_SIZE = 4;
+ constexpr size_t ESCAPE_C_BUFFER_SIZE = 4;
- inline size_t escape_char(
- ui8 c,
- ui8 next,
- ui8 r[ESCAPE_C_BUFFER_SIZE]) {
- // (1) Printable characters go as-is, except backslash and double quote.
- // (2) Characters \r, \n, \t and \0 ... \7 replaced by their simple escape characters (if possible).
- // (3) Otherwise, character is encoded using hexadecimal escape sequence (if possible), or octal.
- if (c == '\"') {
- r[0] = '\\';
- r[1] = '\"';
- return 2;
- } else if (c == '\\') {
- r[0] = '\\';
- r[1] = '\\';
- return 2;
- } else if (is_printable(c)) {
- r[0] = c;
- return 1;
- } else if (c == '\r') {
- r[0] = '\\';
- r[1] = 'r';
- return 2;
- } else if (c == '\n') {
- r[0] = '\\';
- r[1] = 'n';
- return 2;
- } else if (c == '\t') {
- r[0] = '\\';
- r[1] = 't';
- return 2;
- } else if (c < 8 && !is_oct_digit(next)) {
- r[0] = '\\';
- r[1] = oct_digit(c);
- return 2;
- } else if (!is_hex_digit(next)) {
- r[0] = '\\';
- r[1] = 'x';
- r[2] = hex_digit((c & 0xF0) >> 4);
- r[3] = hex_digit((c & 0x0F) >> 0);
- return 4;
- } else {
- r[0] = '\\';
- r[1] = oct_digit((c & 0700) >> 6);
- r[2] = oct_digit((c & 0070) >> 3);
- r[3] = oct_digit((c & 0007) >> 0);
- return 4;
- }
- }
+ inline size_t escape_char(
+ ui8 c,
+ ui8 next,
+ ui8 r[ESCAPE_C_BUFFER_SIZE]) {
+ // (1) Printable characters go as-is, except backslash and double quote.
+ // (2) Characters \r, \n, \t and \0 ... \7 replaced by their simple escape characters (if possible).
+ // (3) Otherwise, character is encoded using hexadecimal escape sequence (if possible), or octal.
+ if (c == '\"') {
+ r[0] = '\\';
+ r[1] = '\"';
+ return 2;
+ } else if (c == '\\') {
+ r[0] = '\\';
+ r[1] = '\\';
+ return 2;
+ } else if (is_printable(c)) {
+ r[0] = c;
+ return 1;
+ } else if (c == '\r') {
+ r[0] = '\\';
+ r[1] = 'r';
+ return 2;
+ } else if (c == '\n') {
+ r[0] = '\\';
+ r[1] = 'n';
+ return 2;
+ } else if (c == '\t') {
+ r[0] = '\\';
+ r[1] = 't';
+ return 2;
+ } else if (c < 8 && !is_oct_digit(next)) {
+ r[0] = '\\';
+ r[1] = oct_digit(c);
+ return 2;
+ } else if (!is_hex_digit(next)) {
+ r[0] = '\\';
+ r[1] = 'x';
+ r[2] = hex_digit((c & 0xF0) >> 4);
+ r[3] = hex_digit((c & 0x0F) >> 0);
+ return 4;
+ } else {
+ r[0] = '\\';
+ r[1] = oct_digit((c & 0700) >> 6);
+ r[2] = oct_digit((c & 0070) >> 3);
+ r[3] = oct_digit((c & 0007) >> 0);
+ return 4;
+ }
+ }
- template <typename T>
- inline void escape_impl(const ui8* str, size_t len, T&& consume) {
- ui8 buffer[ESCAPE_C_BUFFER_SIZE];
+ template <typename T>
+ inline void escape_impl(const ui8* str, size_t len, T&& consume) {
+ ui8 buffer[ESCAPE_C_BUFFER_SIZE];
- size_t i, j;
- for (i = 0, j = 0; i < len; ++i) {
- auto next_char = i + 1 < len ? str[i + 1] : 0;
- size_t rlen = escape_char(str[i], next_char, buffer);
+ size_t i, j;
+ for (i = 0, j = 0; i < len; ++i) {
+ auto next_char = i + 1 < len ? str[i + 1] : 0;
+ size_t rlen = escape_char(str[i], next_char, buffer);
- if (rlen > 1) {
- consume(str + j, i - j);
- j = i + 1;
- consume(buffer, rlen);
- }
- }
-
- if (j > 0) {
- consume(str + j, len - j);
- } else {
- consume(str, len);
- }
- }
- }
- } // namespace NCEscape
- } // namespace NDetail
-}
+ if (rlen > 1) {
+ consume(str + j, i - j);
+ j = i + 1;
+ consume(buffer, rlen);
+ }
+ }
+
+ if (j > 0) {
+ consume(str + j, len - j);
+ } else {
+ consume(str, len);
+ }
+ }
+ }
+ } // namespace NCEscape
+ } // namespace NDetail
+}
generated by cgit v1.2.3 (git 2.25.1) at 2025-03-26 06:57:25 +0000